© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 20-TRANSCODER-HP
    7. 63274
    Prev
    Next
    INDEX
    Explanations

    Miscellaneous topics

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æī£éĻ¤
    -0.29
    æī£
    -0.28
    beck
    -0.27
    /editor
    -0.26
     saturn
    -0.26
    ULK
    -0.25
    enz
    -0.25
    leys
    -0.25
     kort
    -0.24
    аÑĢаÑĤ
    -0.24
    POSITIVE LOGITS
    åĿĩå·²
    0.32
    éĥ½å·²ç»ı
    0.29
     already
    0.27
    éĥ½æĺ¯éĿŀ常
    0.27
    å·²ç»ıæĺ¯
    0.25
     Already
    0.25
    Already
    0.25
    .closest
    0.24
     listening
    0.23
    éĥ½æľīçĿĢ
    0.23
    Activations Density 2.969%

    No Known Activations